Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation

Bingnan Li, Zhitong Gao, Xuming He
Proceedings of the 3rd Machine Learning for Health Symposium, PMLR 225:292-306, 2023.

Abstract

Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift and typically require a significant amount of data for training, which hinders their usage in practice. To address these problems, we propose a novel adaptive domain generalization framework, which integrates a learning-free cross-domain representation based on image gradient maps and a class prior-informed test-time adaptation strategy for mitigating local domain shift. We validate our approach on two multi-modal MRI datasets with six cross-modal segmentation tasks. Across all the task settings, our method consistently outperforms competing approaches and shows a stable performance even with limited training data. Our Codes are available now at https://github.com/cuttle-fish-my/GM-Guided-DG .

Cite this Paper

BibTeX
@InProceedings{pmlr-v225-li23a, title = {Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation}, author = {Li, Bingnan and Gao, Zhitong and He, Xuming}, booktitle = {Proceedings of the 3rd Machine Learning for Health Symposium}, pages = {292--306}, year = {2023}, editor = {Hegselmann, Stefan and Parziale, Antonio and Shanmugam, Divya and Tang, Shengpu and Asiedu, Mercy Nyamewaa and Chang, Serina and Hartvigsen, Tom and Singh, Harvineet}, volume = {225}, series = {Proceedings of Machine Learning Research}, month = {10 Dec}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v225/li23a/li23a.pdf}, url = {https://proceedings.mlr.press/v225/li23a.html}, abstract = {Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift and typically require a significant amount of data for training, which hinders their usage in practice. To address these problems, we propose a novel adaptive domain generalization framework, which integrates a learning-free cross-domain representation based on image gradient maps and a class prior-informed test-time adaptation strategy for mitigating local domain shift. We validate our approach on two multi-modal MRI datasets with six cross-modal segmentation tasks. Across all the task settings, our method consistently outperforms competing approaches and shows a stable performance even with limited training data. Our Codes are available now at https://github.com/cuttle-fish-my/GM-Guided-DG .} }
Endnote
%0 Conference Paper %T Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation %A Bingnan Li %A Zhitong Gao %A Xuming He %B Proceedings of the 3rd Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2023 %E Stefan Hegselmann %E Antonio Parziale %E Divya Shanmugam %E Shengpu Tang %E Mercy Nyamewaa Asiedu %E Serina Chang %E Tom Hartvigsen %E Harvineet Singh %F pmlr-v225-li23a %I PMLR %P 292--306 %U https://proceedings.mlr.press/v225/li23a.html %V 225 %X Cross-modal MRI segmentation is of great value for computer-aided medical diagnosis, enabling flexible data acquisition and model generalization. However, most existing methods have difficulty in handling local variations in domain shift and typically require a significant amount of data for training, which hinders their usage in practice. To address these problems, we propose a novel adaptive domain generalization framework, which integrates a learning-free cross-domain representation based on image gradient maps and a class prior-informed test-time adaptation strategy for mitigating local domain shift. We validate our approach on two multi-modal MRI datasets with six cross-modal segmentation tasks. Across all the task settings, our method consistently outperforms competing approaches and shows a stable performance even with limited training data. Our Codes are available now at https://github.com/cuttle-fish-my/GM-Guided-DG .
APA
Li, B., Gao, Z. & He, X.. (2023). Gradient-Map-Guided Adaptive Domain Generalization for Cross Modality MRI Segmentation. Proceedings of the 3rd Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 225:292-306 Available from https://proceedings.mlr.press/v225/li23a.html.

Related Material